Unlock instant, AI-driven research and patent intelligence for your innovation.

Non-intrusive load identification method based on BiLSTM-CRF algorithm

A load identification, non-intrusive technology, applied in character and pattern recognition, neural learning methods, computing, etc., can solve the problems of inexhaustible and inexhaustible traditional energy, to save electricity and improve model recognition The effect of ability and low cost

Pending Publication Date: 2022-06-28
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the current power generation still relies on burning coal and other traditional energy to generate electricity. However, the traditional energy on the earth is not inexhaustible and inexhaustible

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-intrusive load identification method based on BiLSTM-CRF algorithm
  • Non-intrusive load identification method based on BiLSTM-CRF algorithm
  • Non-intrusive load identification method based on BiLSTM-CRF algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] 1. As attached figure 1 As shown, the present invention comprises the following steps:

[0031] Step 1: Obtain the total power of the electrical equipment from the household outdoor meter device, with a sampling rate of 1Hz, to form the original data set;

[0032] Step 2: Preprocess the data of the original data set in Step 1, and after obtaining a new data set, divide 80% of the data into a training set and 20% into a test set;

[0033] Step 3: Import the data of the training set in Step 2 into the BiLSTM-CRF neural network for training, and obtain the trained model;

[0034] Step 4: Import the test set data in Step 2 into the model of Step 3, test the performance of the model, further optimize the model parameters, and finally generate a load identification model for the BiLSTM-CRF algorithm.

[0035] 2. The preprocessing in step 2 includes the following steps:

[0036] (1) Fill in the vacant value in the original data set, and the filling value is the previous poi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a non-intrusive load identification method based on a BiLSTM-CRF algorithm, and the method comprises the steps: carrying out the sampling of an electric meter, obtaining the power, and constructing an original data set; preprocessing the data, and dividing the data into a training set and a test set; training the training set data through a BiLSTM-CRF network to obtain a model; the performance of the test set data is tested through a model, and model parameters are further optimized; and finally, generating a model for non-intrusive load identification. The method only needs low-frequency sampling data, and is simple in operation, low in cost, high in recognition accuracy and good in generalization ability.

Description

technical field [0001] The invention relates to the field of non-invasive load identification, in particular to a non-invasive load identification method based on a BiLSTM-CRF algorithm. Background technique [0002] As a quiet, hygienic and convenient secondary energy, electric energy plays an increasingly important role in the production and development of human society, and its uses are becoming more and more extensive. Most of the current power generation still relies on burning coal and other traditional energy sources for power generation. However, the traditional energy sources on the earth are not inexhaustible. We need to increase income and reduce expenditure. On the one hand, new methods such as solar energy, wind energy, tidal energy and nuclear energy are used to gradually replace traditional combustion power generation methods. [0003] In recent years, my country's State Grid has put forward the goal of building a smart grid, striving to realize the human-com...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06Q50/06
CPCG06Q50/06G06N3/049G06N3/08G06N3/044G06N3/045G06F18/24G06F18/214
Inventor 竺红卫徐卿杰
Owner ZHEJIANG UNIV